metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
- name: watch-assistant-ft
results: []
watch-assistant-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6518
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9152 | 0.86 | 3 | 0.6749 |
| 0.5722 | 2.0 | 7 | 0.6254 |
| 0.6954 | 2.86 | 10 | 0.6108 |
| 0.4812 | 4.0 | 14 | 0.5827 |
| 0.5823 | 4.86 | 17 | 0.5844 |
| 0.403 | 6.0 | 21 | 0.5804 |
| 0.4876 | 6.86 | 24 | 0.5790 |
| 0.3346 | 8.0 | 28 | 0.6032 |
| 0.4191 | 8.86 | 31 | 0.6084 |
| 0.295 | 10.0 | 35 | 0.6256 |
| 0.3705 | 10.86 | 38 | 0.6355 |
| 0.266 | 12.0 | 42 | 0.6599 |
| 0.2982 | 12.86 | 45 | 0.6518 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2